I am currently an Assistant Professor in Visual Information Processing and Learning (VIPL) group at the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). I received my Ph.D. from ICT, CAS in 2024, under the supervision of Prof. Xilin Chen. I also had close collaboration with Prof. Xiujuan Chai. My research interests mainly focus on human behavior analysis and understanding from sequential data, especially for gesture and sign language. I am also interested in exploring how to use data in deep learning more efficient. Feel free to reach out to me if you have an interest in the relevant topics.
🔥 News
- 2024.06: 🎉🎉 One paper on vision-language pre-training in SLT was accepted by ECCV 2024. Congratulations to Peiqi Jiao and the team!
- 2023.12: 🎉🎉 Successfully defended my PhD dissertation.
- 2023.10: 🎉🎉 One paper on keyframe selection in CSLR was accepted by Scientia Sinica Informationis 2023.
- 2023.10: Present the doctoral consortium “Alignment Constraints for Video-based Sign Language Understanding” at the workshop on Assistive Computer Vision and Robotics at ICCV23 [pdf] [workshop]
- 2023.07: 🎉🎉 One paper on co-occurrence signals in CSLR was accepted by ICCV 2023. Congratulations to Peiqi Jiao and the team!
- 2022.07: 🎉🎉 One paper on sequential representation learning was accepted by ECCV 2022.
📝 Publications
![sym](images/radialCTC.png)
Deep Radial Embedding for Visual Sequence Learning
Yuecong Min, Peiqi Jiao, Yanan Li, Xiaotao Wang, Lei Lei, Xiujuan Chai, Xilin Chen
- RadialCTC constrains sequence features on a hypersphere while retaining the iterative alignment mechanism of CTC, which also provides a clear geometric interpretation for CTC
- RadialCTC controls the peaky behavior with a simple angular perturbation term
![sym](images/vac.png)
Visual Alignment Constraint for Continuous Sign Language Recognition
Yuecong Min, Aiming Hao, Xiujuan Chai, Xilin Chen
- VAC provides an efficient way to make CSLR models end-to-end trainable and is adopted as the baseline model by many recent works
- Two metrics to evaluate the contributions of the feature extractor and the alignment module
![sym](images/pointlstm.png)
An Efficient PointLSTM for Point Clouds Based Gesture Recognition
Yuecong Min, Yanxiao Zhang, Xiujuan Chai, Xilin Chen
- PointLSTM can leverage long-term spatio-temporal relationships in irregular sequence data (e.g., point cloud) while preserving the spatial structure for irregular sequence recognition problem
- Evaluation results on 3D gesture recognition and action recognition show great potential for real-time applications
- Visual Alignment Pre-training for Sign Language Translation. Peiqi Jiao, Yuecong Min, Xilin Chen, accepted by ECCV, 2024.
- Adaptive Keyframe Selection for Continuous Sign Language Recognition. Yuecong Min, Xilin Chen, SCIENTIA SINICA Informationis, 2023.
- CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition. Peiqi Jiao, Yuecong Min, Yanan Li, Xiaotao Wang, Lei Lei, Xilin Chen, International Conference on Computer Vision (ICCV), 2023.
- Self-Mutual Distillation Learning for Continuous Sign Language Recognition. Aiming Hao, Yuecong Min, and Xilin Chen, International Conference on Computer Vision (ICCV), 2021.
- Teaching Chinese Sign Language with A Smartphone. Yanxiao Zhang, Yuecong Min, Xilin Chen, Virtual Reality & Intelligent Hardware, 2021.
- FlickerNet: Adaptive 3D Gesture Recognition from Sparse Point Clouds. Yuecong Min, Xiujuan Chai, Lei Zhao, Xilin Chen, British Machine Vision Conference (BMVC), 2019.
🎖 Honors and Awards
- China National Scholarship for Ph.D., ICT, CAS, 2022
📖 Educations
- 2017.09 - 2024.1, I was a Ph.D. student at Institute of Computing Technology, CAS, under the supervision of Prof. Xilin Chen.
- 2013.09 - 2017.07, I was a college student in Shandong University, Weihai.
✒️ Academic Services
- Invited journal reviewer for IEEE TPAMI / IEEE TMM / IEEE TIP / PR …
- Invited conference reviewer for CVPR’22 /ACM MM’22 / ECCV’22 / CVPR’23 …